SLURP-TN : Resource for Tunisian Dialect Spoken Language Understanding

TL;DR

This paper introduces SLURP-TN, a new Tunisian dialect spoken language understanding dataset with 4165 sentences, enabling development of SLU and ASR models for low-resource dialects, and provides baseline models for future research.

Contribution

The paper presents SLURP-TN, a novel Tunisian dialect SLU dataset, and baseline models, addressing resource scarcity in low-resource language dialects.

Findings

Created a 4165-sentence Tunisian dialect SLU dataset

Developed baseline SLU and ASR models using the dataset

Made dataset and models publicly available

Abstract

Spoken Language Understanding (SLU) aims to extract the semantic information from the speech utterance of user queries. It is a core component in a task-oriented dialogue system. With the spectacular progress of deep neural network models and the evolution of pre-trained language models, SLU has obtained significant breakthroughs. However, only a few high-resource languages have taken advantage of this progress due to the absence of SLU resources. In this paper, we seek to mitigate this obstacle by introducing SLURP-TN. This dataset was created by recording 55 native speakers uttering sentences in Tunisian dialect, manually translated from six SLURP domains. The result is an SLU Tunisian dialect dataset that comprises 4165 sentences recorded into around 5 hours of acoustic material. We also develop a number of Automatic Speech Recognition and SLU models exploiting SLUTP-TN. The Dataset and baseline models are available at: https://huggingface.co/datasets/Elyadata/SLURP-TN.